Imaging Apparatus and Imaging System

1. An imaging apparatus for performing processing of machine learning related to estimation of a distance image closer to reality related to an object than a distance image related to the object captured by an imaging sensor from the distance image, the imaging apparatus comprising: a data acquisition unit for acquiring distance image data related to the object; and a preprocessing unit for creating input data from the distance image data related to the object, wherein processing of machine learning for estimating distance image data close to reality related to the object from the distance image data related to the object is performed using the input data, the preprocessing unit creates teacher data in which the distance image data related to the object is input data and the distance image data close to reality related to the object is output data, and the imaging apparatus further comprises a learning unit for performing supervised learning related to the processing of the machine learning based on the teacher data and generating a learned model for estimating the distance image data close to reality related to the object from the distance image data related to the object.

2. The imaging apparatus according to claim 1 , further comprising an object detection unit for detecting a position and a posture of the object from the distance image data related to the object acquired by the data acquisition unit.

3. The imaging apparatus according to claim 1 , further comprising a CAD data storage unit for storing CAD data related to the object, wherein the preprocessing unit generates the distance image data close to reality related to the object based on the CAD data related to the object stored in the CAD data storage unit.

4. The imaging apparatus according to claim 1 , further comprising: an object detection unit for detecting a position and a posture of the object from the distance image data related to the object acquired by the data acquisition unit; and a CAD data storage unit for storing CAD data related to the object, wherein the preprocessing unit generates distance image data close to reality related to the object based on the CAD data related to the object stored in the CAD data storage unit and the position and the posture of the object detected by the object detection unit.

5. The imaging apparatus according to claim 1 , wherein the preprocessing unit generates distance image data close to reality related to the object based on a distance image related to the object captured by an imaging sensor having higher accuracy than accuracy of the imaging sensor.

6. The imaging apparatus according to claim 1 , wherein the data acquisition unit acquires luminance image data of the object in addition to the distance image data related to the object, and the preprocessing unit uses the distance image data related to the object and the luminance image data as input data.

7. The imaging apparatus according to claim 1 , further comprising: a learning model storage unit storing a learned model for estimating the distance image data close to reality related to the object from the distance image data related to the object; and an estimation unit for estimating the distance image data close to reality related to the object from the distance image data related to the object using the input data and the learned model as the processing of the machine learning.

8. A machine learning processing method of an imaging apparatus performing processing of machine learning for estimating a distance image closer to reality related to an object based on a distance image related to the object captured by an imaging sensor, the machine learning processing method executing: a first step of acquiring distance image data related to the object; a second step of creating input data from the distance image data related to the object; and a third step of performing processing of machine learning for estimating distance image data close to reality related to the object from distance image data related to the object using the input data, wherein the second step is a step of creating teacher data in which the distance image data related to the object is input data and the distance image data close to reality related to the object is output data, and the third step performs supervised learning based on the teacher data and generates a learned model for estimating the distance image data close to reality related to the object from the distance image data related to the object as the processing of the machine learning.

9. The machine learning processing method of the imaging apparatus according to claim 8 , wherein the third step estimates the distance image data close to reality related to the object from the distance image data related to the object using the input data and a learned model for estimating the distance image data close to reality related to the object from the distance image data related to the object as the processing of the machine learning.

10. An imaging system in which a plurality of apparatuses is connected to each other via a network, wherein the plurality of apparatuses includes a first imaging apparatus corresponding to the imaging apparatus according to claim 1 .

11. The imaging system according to claim 10 , wherein the plurality of apparatuses includes a computer including a machine learning device, the computer acquires a learning model as a result of learning of at least one of first imaging apparatuses, and the machine learning device included in the computer performs optimization or streamlining based on the acquired learning model.

12. The imaging system according to claim 10 , wherein the plurality of apparatuses includes a second imaging apparatus different from the first imaging apparatus, and a learning result by the first imaging apparatus is shared with the second imaging apparatus.

13. The imaging system according to claim 10 , wherein the plurality of apparatuses includes a second imaging apparatus different from the first imaging apparatus, and data observed in the second imaging apparatus is available for learning by the first imaging apparatus via the network.

14. An imaging apparatus for performing processing of machine learning related to estimation of a distance image closer to reality related to an object than a distance image related to the object captured by an imaging sensor from the distance image, the imaging apparatus comprising: a processor configured to acquire distance image data related to the object, create input data from the distance image data related to the object, and perform, using the input data, processing of machine learning for estimating distance image data close to reality related to the object from the distance image data related to the object, wherein the processor is further configured to create teacher data in which the distance image data related to the object is input data and the distance image data close to reality related to the object is output data, and perform supervised learning related to the processing of the machine learning based on the teacher data and generate a learned model for estimating the distance image data close to reality related to the object from the distance image data related to the object.

15. The imaging apparatus according to claim 14 , wherein the processor is further configured to detect a position and a posture of the object from the distance image data related to the acquired object.

16. The imaging apparatus according to claim 14 , further comprising a CAD data storage for storing CAD data related to the object, wherein the processor is further configured to generate the distance image data close to reality related to the object based on the CAD data related to the object stored in the CAD data storage.

17. The imaging apparatus according to claim 14 , wherein the processor is further configured to detect a position and a posture of the object from the distance image data related to the acquired object, the imaging apparatus further comprises a CAD data storage for storing CAD data related to the object, and the processor is further configured to generate distance image data close to reality related to the object based on the CAD data related to the object stored in the CAD data storage and the detected position and the detected posture of the object.

18. The imaging apparatus according to claim 14 , wherein the processor is further configured to generate distance image data close to reality related to the object based on a distance image related to the object captured by an imaging sensor having higher accuracy than accuracy of the imaging sensor.

19. The imaging apparatus according to claim 14 , wherein the processor is further configured to acquire luminance image data of the object in addition to the distance image data related to the object, and use the distance image data related to the object and the luminance image data as input data.

20. The imaging apparatus according to claim 14 , further comprising: a learning model storage for storing a learned model for estimating the distance image data close to reality related to the object from the distance image data related to the object, wherein the processor is further configured to estimate the distance image data close to reality related to the object from the distance image data related to the object using the input data and the learned model as the processing of the machine learning.